Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3624. Min Range: -9.3624
Max Act: 9.3624. Min Act: -0.1700
Data Index: 7867359 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3624. Min Range: -9.3624
Max Act: 9.1124. Min Act: -0.1700
Data Index: 682604 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3624. Min Range: -9.3624
Max Act: 9.0499. Min Act: -0.1700
Data Index: 8098504 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.9249. Min Act: -0.1700
Data Index: 4170356 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.7374. Min Act: -0.1700
Data Index: 2747718 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.6749. Min Act: -0.1700
Data Index: 7874318 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.5499. Min Act: -0.1700
Data Index: 4359664 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.6124. Min Act: -0.1700
Data Index: 3577052 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.4249. Min Act: -0.1700
Data Index: 215188 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.4249. Min Act: -0.1700
Data Index: 3778768 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.4249. Min Act: -0.1700
Data Index: 5252737 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.4249. Min Act: -0.1700
Data Index: 1339414 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.3624. Min Act: -0.1700
Data Index: 4079152 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.3624. Min Act: -0.1700
Data Index: 7314309 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.2999. Min Act: -0.1700
Data Index: 2859474 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.2374. Min Act: -0.1700
Data Index: 5248067 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.2374. Min Act: -0.1700
Data Index: 7461678 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.2374. Min Act: -0.1700
Data Index: 1190923 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.1749. Min Act: -0.1700
Data Index: 340927 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3624. Min Range: -9.3624
Max Act: 8.1749. Min Act: -0.1700
Data Index: 2484401 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19